INDEX

Explanations

phrases related to legal matters or policies

oai_token-act-pair · gpt-3.5-turbo

references to legal terminology and discussions surrounding legal cases or frameworks

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isphere

-0.54

EngineDebug

-0.53

ãĥ´ãĤ¡

-0.52

Ø¨

-0.51

ãĥĸ

-0.50

Ö

-0.49

ÙĦ

-0.49

ignt

-0.49

idth

-0.48

ãĤ¨ãĥ«

-0.48

POSITIVE LOGITS

 latter

0.51

 unfortunate

0.51

 discomfort

0.49

cing

0.47

 sadd

0.45

 shaming

0.45

entimes

0.44

 Cards

0.44

 contrast

0.43

AAP

0.43

Activations Density 1.209%

phrases related to legal matters or policies

references to legal terminology and discussions surrounding legal cases or frameworks

No Comments

No Known Activations